Back

Father and son

import pandas as pd
import numpy as np
import plotly.express as px

df=pd.read_excel("fas.xlsx")

In this data set, 1257 product information is collected from the public website.

the analysis made with this data are:

• A timeline that shows how the company's product publishing had changed and the total number of variations in the product.
• The current discount and the selling price range values.
• And the overall difference of the sum of inventory base on the type of sizes (XS, S, M...), and whether it's discounted or not.

df["Publish Date"]=pd.to_datetime(df["Publish Date"], format='%Y-%m-%d')

df.head()

	Unnamed: 0	Title	Label	Selling Prix in £	Original Prix in £	Discount	Link	Img	XS	S	...	30"	32"	34"	36"	38"	38"W	36"W	30"W	32"W	34"W
0	0	'AYLA' Knitted Co ord Crop top Black - CTJ007	No Label	19.99	19.99	0	https://fathersonsclothing.com/collections/all...	https://cdn.shopify.com/s/files/1/0423/8761/pr...	NaN	0.0	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	1	'AYLA' Knitted Co ord Crop top white - CTJ009	No Label	19.99	19.99	0	https://fathersonsclothing.com/collections/all...	https://cdn.shopify.com/s/files/1/0423/8761/pr...	NaN	0.0	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	2	'AYLA' Knitted Co ord Trouser Black - CTJ008	No Label	29.99	29.99	0	https://fathersonsclothing.com/collections/all...	https://cdn.shopify.com/s/files/1/0423/8761/pr...	NaN	1.0	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	3	'AYLA' Knitted Co ord Trouser White - CTJ010	No Label	29.99	29.99	0	https://fathersonsclothing.com/collections/all...	https://cdn.shopify.com/s/files/1/0423/8761/pr...	NaN	2.0	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	4	'CASUAL CLUB' ECRU CROP JUMPER - CT092	On sale	29.99	34.99	14	https://fathersonsclothing.com/collections/all...	https://cdn.shopify.com/s/files/1/0423/8761/pr...	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

5 rows × 67 columns

dd=df.groupby(["Publish Date","Label"]).agg({"# of variants":"sum","Title":"count"}).reset_index()
dd["Year"]=dd["Publish Date"].dt.year
dd["MnD"]=dd["Publish Date"].dt.strftime('%m-%d')
dd["month"]=dd["Publish Date"].dt.month

In mid-2017, the product publishment stayed at a somewhat steady rate.

Back to top

px.line(dd,x="Publish Date",y="Title",color='Label',
        title='Number of products published during the years and their current labeling')

Comparison of the number of the products published in 2019, 2020, and 2021 with their current labeling.

size=300
px.line(dd[(dd["Publish Date"]>"2019-01-01") & (dd["Publish Date"]<"2020-01-01")],x="Publish Date",y="Title",color='Label',
       range_x=["2019-01-01","2019-12-30"],range_y=[0,12], title="2019", height=size).show()
px.line(dd[(dd["Publish Date"]>"2020-01-01") & (dd["Publish Date"]<"2021-01-01")],x="Publish Date",y="Title",color='Label',
       range_x=["2020-01-01","2020-12-30"],range_y=[0,12], title="2020", height=size).show()
px.line(dd[(dd["Publish Date"]>"2021-01-01")],x="Publish Date",y="Title",color='Label',
       range_x=["2021-01-01","2021-12-30"],range_y=[0,12], title="2021", height=size).show()

Comparison of the number of the product variations published in 2019, 2020, and 2021 with their current labeling.

size=300
px.line(dd[(dd["Publish Date"]>"2019-01-01") & (dd["Publish Date"]<"2020-01-01")],x="Publish Date",y="# of variants",color='Label',
       range_x=["2019-01-01","2019-12-30"],range_y=[0,120], title="2019", height=size).show()
px.line(dd[(dd["Publish Date"]>"2020-01-01") & (dd["Publish Date"]<"2021-01-01")],x="Publish Date",y="# of variants",color='Label',
       range_x=["2020-01-01","2020-12-30"],range_y=[0,120], title="2020", height=size).show()
px.line(dd[(dd["Publish Date"]>"2021-01-01")],x="Publish Date",y="# of variants",color='Label',
       range_x=["2021-01-01","2021-12-30"],range_y=[0,120], title="2021", height=size).show()

The products discount range is commonly between 15% and 30% with 2 outliers that receive discount up to 59% and 67% with a selling price of 20£ and 15£.

Back to top

ddd=df[df['Label']=="On sale"]
px.box(ddd,x="Discount",hover_data=["Title","Publish Date","Selling Prix in £"],height=300)

The products selling price range for each group of labels.

px.box(df,x="Selling Prix in £",hover_data=["Title","Publish Date","Discount"],color='Label',height=400)

Number of product according to the current labels

px.bar(df['Label'].value_counts().reset_index().rename(columns={"index": "Label", "Label": "count"}),x="Label",y="count")

no_lab=df[df["Label"]=='No Label'][["XS","S","S/M","M","M/L","L","XL","XXL","XXXL","XXXXL","6","8","10","12","14","16","18","Default","ONE",
         "6-W24","8-W26","10-W28","12-W30","14-W32","16-W34","3 Years","4 Years","5 Years","6 Years","7 Years","8 Years",
          "9 Years","10 Years","11 Years","12 Years"]].sum().reset_index().rename(columns={"index": "size", 0: "count"})
no_lab["Label"]="No Label"

on_s=df[df["Label"]=='On sale'][["XS","S","S/M","M","M/L","L","XL","XXL","XXXL","XXXXL","6","8","10","12","14","16","18","Default","ONE",
         "6-W24","8-W26","10-W28","12-W30","14-W32","16-W34","3 Years","4 Years","5 Years","6 Years","7 Years","8 Years",
          "9 Years","10 Years","11 Years","12 Years"]].sum().reset_index().rename(columns={"index": "size", 0: "count"})
on_s["Label"]="On sale"

df3=pd.concat([no_lab,on_s])

df3.head()

	size	count	Label
0	XS	3993.0	No Label
1	S	8523.0	No Label
2	S/M	14.0	No Label
3	M	11273.0	No Label
4	M/L	31.0	No Label

Inventory quantity comparison of each group of sizes for products with and without discount currently.

Back to top

px.bar(df3,x="count",y="size",color="Label", barmode='group', height=800)